Hugging Face's logo

stewy33
/
8B-20k_original_augmented_original_subtle_antarctic_rebound-49711925

PEFT
Safetensors
Model card Files Community
8B-20k_original_augmented_original_subtle_antarctic_rebound-49711925
File size: 2,821 Bytes 
7bac1af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 11,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.026356816291809,
      "learning_rate": 1e-05,
      "loss": 2.3963,
      "step": 1
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.9992382526397705,
      "learning_rate": 9.090909090909091e-06,
      "loss": 2.3933,
      "step": 2
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.9592933058738708,
      "learning_rate": 8.181818181818183e-06,
      "loss": 2.3729,
      "step": 3
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.9365403056144714,
      "learning_rate": 7.272727272727273e-06,
      "loss": 2.3621,
      "step": 4
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.8861187696456909,
      "learning_rate": 6.363636363636364e-06,
      "loss": 2.303,
      "step": 5
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.8701594471931458,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 2.3215,
      "step": 6
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.854203999042511,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 2.287,
      "step": 7
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.8238375782966614,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 2.2769,
      "step": 8
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.8066386580467224,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 2.262,
      "step": 9
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.7800577878952026,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 2.2257,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7961292862892151,
      "learning_rate": 9.090909090909091e-07,
      "loss": 2.2574,
      "step": 11
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.3213725090026855,
      "eval_runtime": 5.2102,
      "eval_samples_per_second": 0.576,
      "eval_steps_per_second": 0.192,
      "step": 11
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 11,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.601034612028211e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}